Reinforcement learning is a machine learning method particularly interesting for the autonomous driving domain, as it enables autopilot training without the need for large and expensive amounts of manually labeled training data. Instead, agents are trained by evaluating the effects of their actions and punishing or rewarding them accordingly. In autonomous and particularly cooperative driving a core problem is however that multiple vehicles need to be trained in parallel while having an impact on each other's behavior. In this paper, we present a simulation solution providing cooperative training capabilities out-of-the-box and compare the quality of the resulting autopilots in an intersection scenario.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MontiSim: Agent-Based Simulation for Reinforcement Learning of Autonomous Driving


    Contributors:


    Publication date :

    2023-09-24


    Size :

    368809 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Robustness of reinforcement learning based autonomous driving technologies

    Hart, Fabian / Technische Universität Dresden | SLUB | 2024


    Autonomous Driving with Deep Reinforcement Learning

    Zhu, Yuhua / Technische Universität Dresden | SLUB | 2023


    Synthesizing Data for Autonomous Driving: Multi-Agent Reinforcement Learning Meets Augmented Reality

    Meng, Chao / Wang, Hanchao / Mei, Jinren et al. | SAE Technical Papers | 2023


    Robustness of reinforcement learning based autonomous driving technologies

    Hart, Fabian / Technische Universität Dresden | TIBKAT | 2024

    Free access

    Robustness of reinforcement learning based autonomous driving technologies

    Hart, Fabian / Technische Universität Dresden | SLUB | 2024